Sven Mika
|
52c94b7ee9
[RLlib] Allow SAC to use custom models as Q- or policy nets and deprecate "state-preprocessor" for image spaces. (#13522)
|
3 years ago |
Sven Mika
|
93c0a5549b
[RLlib] Deprecate `vf_share_layers` in top-level PPO/MAML/MB-MPO configs. (#13397)
|
3 years ago |
Sven Mika
|
9dd9f72111
[RLlib] Add more detailed Documentation on Model building API (#13261)
|
3 years ago |
Sven Mika
|
9eba1871bb
[RLlib] Support easy `use_attention=True` flag for using the GTrXL model. (#11698)
|
3 years ago |
Sven Mika
|
391cdfae8c
[RLlib] Trajectory view API docs. (#12718)
|
3 years ago |
Sven Mika
|
fe0bdb23ff
[RLlib] Attention Net/Transformers docs improvement.
|
4 years ago |
Sven Mika
|
66d204e078
[RLlib] Model documentation enhancements. (#10011)
|
4 years ago |
Eric Liang
|
be26a7b1b0
[rllib] Support for complex / variable-length observation spaces (#8393)
|
4 years ago |
Sven Mika
|
c74dc58f8b
[RLlib] Fix `use_lstm` flag for ModelV2 (w/o ModelV1 wrapping) and add it for PyTorch. (#8734)
|
4 years ago |
Sven Mika
|
2746fc0476
[RLlib] Auto-framework, retire `use_pytorch` in favor of `framework=...` (#8520)
|
4 years ago |
Sven Mika
|
0422e9c5a8
[RLlib] Add 2 Transformer learning test cases on StatelessCartPole (PPO and IMPALA). (#8624)
|
4 years ago |
Eric Liang
|
9a83908c46
[rllib] Deprecate policy optimizers (#8345)
|
4 years ago |
Sven Mika
|
796a834c48
[RLlib] Attention Net integration into ModelV2 and learning RL example. (#8371)
|
4 years ago |
Sven Mika
|
42991d723f
[RLlib] rllib/examples folder restructuring (#8250)
|
4 years ago |
Eric Liang
|
fbc545c03b
[rllib] Support parallel, parameterized evaluation (#6981)
|
4 years ago |
Eric Liang
|
a229bdf272
[rllib] Deprecate custom preprocessors (#6833)
|
4 years ago |
Shital Shah
|
670cb6374e
Doc enhancement: use build.sh for ray, clarification on how rllib selects VisionNetwork, note on setup-dev.py for rllib. (#6092)
|
4 years ago |
Olli Huotari
|
0916603e61
Fixed few broken links in docs (#5477)
|
5 years ago |
Eric Liang
|
a1d2e17623
[rllib] Autoregressive action distributions (#5304)
|
5 years ago |
Eric Liang
|
5d7afe8092
[rllib] Try moving RLlib to top level dir (#5324)
|
5 years ago |
Eric Liang
|
a62c5f40f6
[rllib] Document ModelV2 and clean up the models/ directory (#5277)
|
5 years ago |
Eric Liang
|
bf9199ad77
[rllib] ModelV2 support for pytorch (#5249)
|
5 years ago |
Eric Liang
|
34d054ff19
[rllib] ModelV2 API (#4926)
|
5 years ago |
Eric Liang
|
2dd0beb5bd
[rllib] Allow access to batches prior to postprocessing (#4871)
|
5 years ago |
Eric Liang
|
02583a8598
[rllib] Rename PolicyGraph => Policy, move from evaluation/ to policy/ (#4819)
|
5 years ago |
Eric Liang
|
3807fb505b
[rllib] TensorFlow 2 compatibility (#4802)
|
5 years ago |
Eric Liang
|
37208216ae
[rllib] Rename Agent to Trainer (#4556)
|
5 years ago |
Eric Liang
|
ba03048254
[rllib] TF model custom_loss() should actually allow access to full rollout data (#4220)
|
5 years ago |
Robert Nishihara
|
4b89eebfc7
Move test folders under rllib/tune from test -> tests. (#4214)
|
5 years ago |
Eric Liang
|
d9da183c7d
[rllib] Custom supervised loss API (#4083)
|
5 years ago |